Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4045 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.9621. Min Act: -0.0001

Data Index: 143865 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.8474. Min Act: -0.0001

Data Index: 1067613 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.7687. Min Act: -0.0001

Data Index: 744175 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.7400. Min Act: -0.0001

Data Index: 1188244 (C4 (Web Text))

Max Activating Token Index: 422

Text #4

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.6213. Min Act: -0.0001

Data Index: 164753 (C4 (Web Text))

Max Activating Token Index: 787

Text #5

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.4223. Min Act: -0.0001

Data Index: 1350847 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.6579. Min Act: -0.0001

Data Index: 1166486 (C4 (Web Text))

Max Activating Token Index: 63

Text #7

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.4625. Min Act: -0.0001

Data Index: 237916 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.8456. Min Act: -0.0001

Data Index: 1430535 (Python Code)

Max Activating Token Index: 187

Text #9

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.6344. Min Act: -0.0001

Data Index: 1428449 (Python Code)

Max Activating Token Index: 643

Text #10

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.4613. Min Act: -0.0001

Data Index: 802542 (C4 (Web Text))

Max Activating Token Index: 598

Text #11

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.5029. Min Act: -0.0001

Data Index: 856357 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.5212. Min Act: -0.0001

Data Index: 356636 (C4 (Web Text))

Max Activating Token Index: 464

Text #13

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.3386. Min Act: -0.0001

Data Index: 1357842 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.5925. Min Act: -0.0001

Data Index: 194034 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.4126. Min Act: -0.0001

Data Index: 1553840 (Python Code)

Max Activating Token Index: 727

Text #16

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.4777. Min Act: -0.0001

Data Index: 977210 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.6624. Min Act: -0.0001

Data Index: 112132 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.3774. Min Act: -0.0001

Data Index: 484652 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 1.9621. Min Range: -1.9621

Max Act: 1.5632. Min Act: -0.0001

Data Index: 137232 (C4 (Web Text))

Max Activating Token Index: 234